© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23890
    Prev
    Next
    INDEX
    Explanations

    words related to the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Entertainment."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĻĤ
    -0.74
    ients
    -0.72
    xual
    -0.71
    ippy
    -0.69
    htaking
    -0.69
    ought
    -0.69
    ym
    -0.68
    oward
    -0.67
    headed
    -0.67
    cone
    -0.67
    POSITIVE LOGITS
     Entertainment
    1.05
     Enterprises
    1.02
     Services
    0.90
     Corp
    0.84
     Properties
    0.84
     Corporation
    0.84
     Television
    0.83
     Devices
    0.83
     Publishing
    0.81
     Industry
    0.81
    Activations Density 0.009%

    No Known Activations